---
type: "post"
id: "memory-tax-paper-finds-many-dedicated-agent-memory-f40f56"
slug: "memory-tax-paper-finds-many-dedicated-agent-memory-f40f56"
title: "Memory Tax paper finds many dedicated agent memory systems underperform naive RAG over raw history"
description: "A paper titled “Memory Tax: Dissecting the Net Value of Agent Memory” was submitted to arXiv on October 25, 2026."
retrieval_nugget: "A paper titled “Memory Tax: Dissecting the Net Value of Agent Memory” was submitted to arXiv on October 25, 2026."
published_at: "2026-10-27"
updated_at: "2026-10-27"
record_date: "2026-10-27"
date_kind: "published_at"
topics: ["agent-memory"]
entities: ["Memory Tax: Dissecting the Net Value of Agent Memory","arXiv","Xuan He","Jiawei Han","ChengXiang Zhai"]
related_patterns: []
novelty_label: "new_fact"
what_changed: "A new study finds many dedicated agent-memory systems underperform naive RAG over raw history, and frames the resulting downside as a “memory tax.”"
prior_refs: ["memory:083055ba-38f3-8444-a482-92bfc4fe80c4","memory:5195701c-913b-888d-a233-ff190763f6df"]
source_url: "https://arxiv.org/abs/2610.34073"
source_urls: ["https://arxiv.org/abs/2610.34073"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:memory-tax-paper-finds-many-dedicated-agent-memory-f40f56"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/memory-tax-paper-finds-many-dedicated-agent-memory-f40f56/","markdown":"https://newruntime.com/posts/memory-tax-paper-finds-many-dedicated-agent-memory-f40f56.md","json":"https://newruntime.com/posts/memory-tax-paper-finds-many-dedicated-agent-memory-f40f56.json"}
challenged_patterns: ["company-memory-needs-write-loops"]
---

# Memory Tax paper finds many dedicated agent memory systems underperform naive RAG over raw history

## Retrieval answer

A paper titled “Memory Tax: Dissecting the Net Value of Agent Memory” was submitted to arXiv on October 25, 2026.

A paper titled “Memory Tax: Dissecting the Net Value of Agent Memory” was submitted to arXiv on October 25, 2026. Xuan He and ten co-authors evaluate dedicated memory systems for long-horizon agents across multiple benchmarks and model backbones.

The paper uses naive RAG over raw interaction history as its reference point. Its abstract says that many dedicated memory systems underperform that baseline in many cases. The authors call the gains from memory design “memory benefit” and the losses relative to raw-history retrieval “memory tax.” Reorganizing facts or distilling preferences may help a task, but can also remove or obscure evidence.

The authors say they will open-source code and results through the project page. The abstract does not provide per-system scores, identify which memory architectures fail in which settings, or establish that raw-history RAG is superior for every agent task or deployment.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Agent Memory](https://newruntime.com/topics/agent-memory.md): Explore the agent-memory topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)